teach-impeccable
Pass
Audited by Gen Agent Trust Hub on May 8, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: Indirect prompt injection surface: The skill processes untrusted content from the codebase to synthesize design documentation.\n
- Ingestion points: Project documentation, package.json, component files, and brand assets identified during Step 1.\n
- Boundary markers: Absent; there are no instructions to disregard embedded commands in ingested data.\n
- Capability inventory: File read access to the project directory and file write access to .impeccable.md and user configuration files.\n
- Sanitization: Absent; findings are summarized directly into the design context.\n- [COMMAND_EXECUTION]: The skill writes information to the local filesystem, creating or updating .impeccable.md and the project configuration file.
Audit Metadata